Wall-hanging stove temperature control method and device, electronic equipment and storage medium
By constructing a dataset of wall-hung boilers and using machine learning models to predict future temperature demands, the heating temperature is automatically adjusted, solving the problem of manual adjustment of the heating temperature of wall-hung boilers and achieving energy-saving and efficient temperature control.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- MIDEA GROUP CO LTD
- Filing Date
- 2023-08-16
- Publication Date
- 2026-07-24
AI Technical Summary
The heating temperature of existing wall-hung boilers needs to be manually adjusted, which is inconvenient and leads to energy waste.
By building a dataset of wall-hung boilers, combining historical usage data and weather data, machine learning models are used to predict future temperature demands and automatically adjust heating temperatures.
This improves the efficiency of temperature control in wall-hung boilers, saves electricity, and avoids waste of electrical resources.
Smart Images
Figure CN117073057B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of equipment control technology, and in particular to temperature control methods, devices, electronic equipment and storage media for wall-hung boilers. Background Technology
[0002] A wall-hung boiler is a gas-fired boiler that provides both heating and hot water. Currently, the heating temperature of a wall-hung boiler is usually set by the user using buttons on the boiler's display panel or a remote control. Users need to manually adjust the temperature before use and manually turn off the boiler when heating is finished, which is inconvenient. Furthermore, the option to run the boiler 24 hours a day results in significant energy waste. Summary of the Invention
[0003] This application aims to address at least one of the technical problems existing in the prior art. To this end, this application proposes a wall-hung boiler temperature control method, which predicts the user's heating behavior of the wall-hung boiler in the coming day based on the usage behavior of the wall-hung boiler, as well as weather data and holiday data. Then, based on the prediction results and prediction duration, the set temperature of the wall-hung boiler is determined. Based on this, manual setting of the heating temperature is avoided, the efficiency of wall-hung boiler temperature control is improved, and electricity is saved, avoiding waste of electrical resources.
[0004] This application also proposes a temperature control device, electronic equipment, and storage medium for a wall-hung boiler.
[0005] The wall-hung boiler temperature control method according to the first aspect of this application includes:
[0006] Construct a dataset for the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler;
[0007] Based on the dataset, predict the temperature of the wall-hung boiler in future time periods;
[0008] Based on the temperatures and predicted durations for each future time period, the set temperatures for the wall-hung boiler are determined for each future time period, so as to control the temperature of the wall-hung boiler based on the set temperatures for each future time period.
[0009] According to one embodiment of this application, predicting the temperature of the wall-hung boiler in future time periods based on the dataset includes:
[0010] The dataset is input into the first prediction model to obtain the probability of the wall-hung boiler being used in each future time period, as output by the first prediction model.
[0011] The usage probability is determined as a first probability value, and a subset of the dataset is input into a second prediction model to obtain the temperature of the wall-hung boiler in future time periods output by the second prediction module.
[0012] Wherein, the usage probability is a first probability value representing the use of the wall-hung boiler; the subset of the dataset includes historical usage data and historical weather data corresponding to each historical usage time period for which the usage probability is the first probability value; the first prediction model is obtained by training on a first sample set, which includes historical sample usage data and historical sample weather data corresponding to each historical sample usage time period for the wall-hung boiler; the second prediction model is obtained by training on a second sample set, which includes historical sample usage data and historical sample weather data corresponding to each historical sample usage time period for which the usage probability is the first probability value.
[0013] According to one embodiment of this application, determining the set temperature of the wall-hung boiler at any future time period includes:
[0014] If the predicted duration is determined to be less than the first set duration, the temperature output by the second prediction model shall be used as the set temperature of the wall-hung boiler for any future time period.
[0015] Alternatively, if the predicted duration is greater than or equal to the first set duration, the set temperature of the wall-hung boiler in any future time period is determined based on the temperatures of multiple consecutive time periods output by the second prediction model.
[0016] According to one embodiment of this application, determining the set temperature of the wall-hung boiler for any future time period based on the temperatures of multiple consecutive time periods output by the second prediction model includes:
[0017] Determine the average temperature corresponding to the temperature of multiple consecutive time periods output by the second prediction model;
[0018] The average temperature is used as the set temperature of the wall-hung boiler for any future time period.
[0019] According to one embodiment of this application, after inputting the dataset into a first prediction model and obtaining the usage probability of the wall-hung boiler in future time periods output by the first prediction model, the method further includes:
[0020] The usage probability is determined as a second probability value, and the set temperature of the wall-hung boiler in future time periods is determined as the lowest temperature; the usage probability as a second probability value indicates that the wall-hung boiler is not used.
[0021] According to one embodiment of this application, the process of constructing the dataset for the wall-hung boiler includes:
[0022] Obtain the usage time of the wall-hung boiler;
[0023] If the usage duration is determined to be greater than or equal to the second set duration, then historical usage data and historical weather data corresponding to each historical usage time period of the wall-hung boiler are collected to construct the dataset of the wall-hung boiler.
[0024] According to one embodiment of this application, the temperature control of the wall-hung boiler based on the set temperatures for the future time periods includes:
[0025] Determine the time to send the temperature control command;
[0026] Based on the set temperatures for each future time period and the sending time, the temperature control command is sent to the wall-hung boiler; wherein, the wall-hung boiler adjusts the temperature based on the received temperature control command.
[0027] The wall-hung boiler temperature control device according to a second aspect embodiment of this application includes:
[0028] The construction module is used to build the dataset of the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler;
[0029] The prediction module is used to predict the temperature of the wall-hung boiler in future time periods based on the dataset.
[0030] The control module is used to determine the set temperature of the wall-hung boiler in the future time period based on the temperature and predicted duration of each future time period, so as to perform temperature control on the wall-hung boiler based on the set temperature of each future time period.
[0031] An electronic device according to a third aspect of this application includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the wall-hung boiler temperature control method as described above.
[0032] A non-transitory computer-readable storage medium according to a fourth aspect of this application stores a computer program thereon, which, when executed by a processor, implements the wall-hung boiler temperature control method as described above.
[0033] The above-described one or more technical solutions in the embodiments of this application have at least one of the following technical effects:
[0034] This avoids manually setting the heating temperature, improves the efficiency of temperature control in wall-hung boilers, saves electricity, and avoids wasting power resources.
[0035] Additional aspects and advantages of this application will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of this application. Attached Figure Description
[0036] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0037] Figure 1 This is one of the flowcharts illustrating the wall-hung boiler temperature control method provided in the embodiments of this application;
[0038] Figure 2 This is a second schematic flowchart of the wall-hung boiler temperature control method provided in the embodiments of this application;
[0039] Figure 3 This is a schematic diagram of the wall-hung boiler temperature control device provided in the embodiments of this application;
[0040] Figure 4 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application. Detailed Implementation
[0041] The embodiments of this application will be described in further detail below with reference to the accompanying drawings and examples. The following examples are used to illustrate this application, but should not be used to limit the scope of this application.
[0042] In the description of the embodiments of this application, it should be noted that the terms "first", "second" and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.
[0043] In the embodiments of this application, unless otherwise expressly specified and limited, "above" or "below" the second feature can mean that the first feature is in direct contact with the second feature, or that the first feature is in indirect contact with the second feature through an intermediate medium. Furthermore, "above," "on top of," and "over" the second feature can mean that the first feature is directly above or diagonally above the second feature, or simply that the first feature is at a higher horizontal level than the second feature. "Below," "below," and "under" the second feature can mean that the first feature is directly below or diagonally below the second feature, or simply that the first feature is at a lower horizontal level than the second feature.
[0044] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the embodiments of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.
[0045] Figure 1 This is one of the flowcharts illustrating the wall-hung boiler temperature control method provided in this application. (Refer to...) Figure 1 This application provides a method for controlling the temperature of a wall-hung boiler, including:
[0046] Step 100: Construct a dataset for the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler.
[0047] Historical usage data and historical weather data corresponding to various historical usage periods of the wall-hung boiler are collected, and then a dataset for the wall-hung boiler is constructed based on the collected data. The historical usage period can refer to different time periods within a day, such as 8:00-9:00, 10:00-11:00, 12:00-13:00; or different time periods within a week, such as Monday, Tuesday, Wednesday, etc.
[0048] For example, (1) Select the historical usage data reported by the wall-hung boiler in the most recent year, and obtain the identification information of the wall-hung boiler (such as equipment ID), the city identification information of the city where the wall-hung boiler is located (such as city ID), the data reporting date, and the set temperature for each hour based on the historical usage data. For each hour, if the user uses the heating function of the wall-hung boiler in that hour, the field "Whether the wall-hung boiler heating function is turned on in that hour" is set to 1, otherwise it is 0; the value of the field "Set temperature of the wall-hung boiler in that hour" comes from the average set temperature of each hour in the electrical control reporting data of the wall-hung boiler. The processed data is shown in the table below:
[0049]
[0050] (2) Collect historical weather data for the area where the wall-hung boiler is located for the past year. Based on this historical weather data, determine the highest and lowest temperatures for each day in history. Compare the temperature rise of the highest temperature the previous day with the temperature rise of the lowest temperature the previous day, and generate the following data table based on this information:
[0051]
[0052] (3) Collect the historical usage time period of the wall-hung boiler for the most recent year, perform feature processing on the date data corresponding to the historical usage time period, and generate the following data table:
[0053]
[0054]
[0055]
[0056] (4) Integrate the data generated in steps (1)-(3) to generate the following data table:
[0057] Feature data table of the prediction model for whether the heating function is turned on:
[0058] hour_to_dense temperature_min temperature_max day of month heating_water_temp_avg_2 std_7
[0059] Heating system temperature prediction model feature data table:
[0060] sim_time_set_temp mean_3 isna_sim_one_day hour_to_dense
[0061] Based on the historical usage data and historical weather data of the wall-hung boilers for each historical usage period, the above table is used to construct a dataset for the wall-hung boilers.
[0062] Optionally, to improve the prediction accuracy of the prediction model, when constructing the dataset, it is necessary to determine the usage duration of the wall-hung boiler. If the usage duration is greater than or equal to the set duration, historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler are collected to construct the dataset of the wall-hung boiler.
[0063] For example, assuming a usage period of 14 days, for wall-hung boilers used for less than 14 days, their corresponding historical data is directly filtered out and not included in the model construction; for wall-hung boilers used for 14 days or more, their historical data is collected to construct a dataset for the boiler. Based on this, using historical data from boilers used for 14 days or more can provide information about user habits, time patterns, and temperature preferences, helping to understand user needs, provide personalized services and suggestions, and improve the prediction accuracy of the predictive model, thereby improving the accuracy of the boiler's set temperature.
[0064] Step 200: Based on the dataset, predict the temperature of the wall-hung boiler in future time periods;
[0065] After constructing the dataset, it is input into a pre-built prediction model, and the model outputs the temperature of the wall-hung boiler for each future time period. For example, the dataset is used to predict the hourly temperature of the wall-hung boiler for the next day.
[0066] Step 300: Based on the temperature and predicted duration of each future time period, determine the set temperature of the wall-hung boiler for each future time period, so as to control the temperature of the wall-hung boiler based on the set temperature of each future time period.
[0067] It should be noted that due to the existence of model prediction errors, there may be situations where the set temperature fluctuates drastically. To solve this problem, a moving average method is used for smoothing, which helps to smooth the temperature prediction value, reduce drastic fluctuations, and improve the accuracy and stability of temperature prediction.
[0068] Based on the predicted temperatures and durations for different time periods in the future, the set temperatures for the wall-hung boiler are determined for each period, allowing for temperature control of the boiler. The predicted duration refers to the time span considered when predicting the temperature; different predicted durations correspond to different set temperatures. For example, assuming the predicted temperature is 60℃ from 00:00 to 01:00 on the second day, and the predicted duration is 1 hour, the set temperature for this period would be 60℃.
[0069] To ensure timely heating for users, the wall-hung boiler needs to be pre-controlled. Specifically, the time for sending temperature control commands is determined. Based on the set temperatures for future time periods and the sending time, temperature control commands are sent to the boiler. The boiler then adjusts the heating temperature based on the received commands. For example, assuming the set temperature is 65℃ from 01:00 to 02:00 the next day, a temperature control command containing the boiler's set temperature is sent to the boiler at 00:55 the following day. Upon receiving this command, the boiler controls the heating based on its own temperature, thus achieving temperature control.
[0070] Optionally, when the wall-hung boiler is not needed, it can be automatically set to energy-saving insulation or shut-off mode to avoid resource waste.
[0071] The wall-hung boiler temperature control method provided in this application constructs a dataset for the wall-hung boiler, which includes historical usage data and historical weather data corresponding to various historical usage periods of the boiler. Based on the dataset, the method predicts the boiler's temperature for future time periods. Based on the future temperatures and prediction durations, it determines the set temperatures for the boiler for each future time period, thereby controlling the boiler's temperature. This application predicts user behavior regarding the boiler's heating function in the coming day based on boiler usage behavior, weather data, and holiday data. Then, based on the prediction results and prediction durations, it determines the boiler's set temperature. This avoids manually setting the heating temperature, improves the efficiency of boiler temperature control, saves electricity, and avoids wasting electrical resources.
[0072] Based on the above embodiments, predicting the temperature of the wall-hung boiler in future time periods based on the dataset includes:
[0073] Step 210: Input the dataset into the first prediction model to obtain the probability of the wall-hung boiler being used in each future time period as output by the first prediction model;
[0074] Step 220: Determine the usage probability as a first probability value, input a subset of the dataset into the second prediction model, and obtain the temperature of the wall-hung boiler in future time periods output by the second prediction module;
[0075] It should be noted that the probability of using a wall-hung boiler is represented by the first probability value; for example, if the first probability value is 1, then it represents the use of a wall-hung boiler.
[0076] A subset of the dataset includes historical usage data and historical weather data corresponding to each historical usage time period with a usage probability of the first probability value. In other words, the subset of the dataset includes historical usage data and historical weather data corresponding to each historical usage time period for which there are records of wall-hung boiler usage. For example, suppose the usage probabilities of the wall-hung boiler at multiple time periods during a day are as shown in the table below:
[0077] 1 1 1 0 1
[0078] In the table above, a usage probability of 1 indicates that the wall-hung boiler was used for heating during that time period; a usage probability of 0 indicates that the wall-hung boiler was not used for heating during that time period. Thus, the subset of the dataset includes historical usage data and historical weather data for the time periods 00:00-01:00, 01:00-02:00, 02:00-03:00, and 04:00-05:00.
[0079] The first prediction model is obtained by training on a first sample set, which includes historical usage data and historical weather data corresponding to various historical usage time periods of the wall-hung boiler. The target variable of the first prediction model is whether the wall-hung boiler is used within that hour. For example, the first sample set can be used to train a DecisionTree model, such as a decision tree classifier, enabling it to learn the relationship between features and categories and make classification decisions. Optionally, the performance of the trained first prediction model can be evaluated using a test set, such as using metrics like accuracy, precision, recall, and F1 score. Then, based on the model evaluation results, the parameters of the first prediction model can be fine-tuned to further improve the model's performance and generalization ability.
[0080] The second prediction model is obtained by training on a second sample set, which includes historical sample usage data and historical sample weather data corresponding to the usage time periods of each historical sample with a usage probability of the first probability value. The target variable of the second prediction model is the temperature of the wall-hung boiler. For example, the first sample set can be used to train a DecisionTree model, such as training a decision tree regressor, enabling it to learn the relationship between features and values and perform regression predictions. Optionally, the performance of the trained second prediction model can be evaluated using a test set, for example, using metrics such as mean squared error, root mean square error, and coefficient of determination. Then, based on the model evaluation results, the parameters of the second prediction model can be fine-tuned to further improve the model's performance and generalization ability.
[0081] After constructing the dataset, it is input into the first prediction model to obtain the usage probability of the wall-hung boiler in each future time period. If the usage probability is the first probability value, a subset of the dataset is input into the second prediction model to obtain the temperature of the wall-hung boiler in each future time period. For example, the prediction results of the first prediction model (i.e., the decision tree classifier model) are displayed in the form of probability values. According to the experimental results, the probability value of a user turning on the heating function of the wall-hung boiler is less than or equal to 0.272. At this time, the decision tree classifier model misclassifies that the number of users who do not actually use the wall-hung boiler is 5% of all data, and considers the user turning on the heating function as a low-probability event, directly setting the minimum temperature to 30℃. When the probability value of a user turning on the heating function of the wall-hung boiler is set to be greater than 0.272, it is judged that the user is using the heating function of the wall-hung boiler. At this time, this part of the user data is input into the second prediction model (i.e., the decision tree regressor model) for prediction, and finally the predicted temperature is processed by moving average.
[0082] Optionally, if the usage probability is the second probability value, indicating that the wall-hung boiler is not used, then the set temperature of the wall-hung boiler for future time periods will be determined as the lowest temperature. For example, if the usage probability is 0, it means that the user will not use the wall-hung boiler within that hour, then the temperature of the wall-hung boiler will be set to the lowest temperature, such as 30°C.
[0083] In this application embodiment, after predicting the use of the wall-hung boiler within a certain hour using a first prediction model, the heating temperature of the wall-hung boiler within that hour is then predicted using a second prediction model. Based on this, the accuracy of the heating temperature prediction is improved.
[0084] Based on the above embodiments, determining the set temperature of the wall-hung boiler at any future time period includes:
[0085] Step 310: Determine that the prediction duration is less than the first set duration, and use the temperature output by the second prediction model as the set temperature of the wall-hung boiler for any future time period;
[0086] Step 320: Determine that the predicted duration is greater than or equal to the first set duration, and determine the set temperature of the wall-hung boiler for any future time period based on the temperatures of multiple consecutive time periods output by the second prediction model.
[0087] If the predicted duration is less than the first set duration (e.g., 2 hours), the temperature output by the second prediction model will be used directly as the set temperature of the wall-hung boiler. For example, if the predicted temperature for the period from 00:00 to 01:00 on the second day is 60℃ and the predicted duration is 1 hour, then 60℃ will be used directly as the set temperature for the period from 00:00 to 01:00.
[0088] If the predicted duration is greater than or equal to the first set duration (e.g., 2 hours), the set temperature of the wall-hung boiler for any future time period is determined based on the temperatures of multiple consecutive time periods output by the second prediction model. Specifically, the average temperature corresponding to the temperatures of multiple consecutive time periods output by the second prediction model is determined, and then the average temperature is used as the set temperature of the wall-hung boiler for any future time period. For example, assuming the predicted duration is greater than 2 hours, the predicted temperature within hour t is v. t The predicted temperatures for the two hours preceding hour t are v, respectively. t-1 and v t-2 Then the set temperature for hour t is (v t +v t-1 +v t-2 For example, if the predicted temperatures for the three time periods of 00:00-01:00, 01:00-02:00, and 02:00-03:00 on the second day are 60℃, 55℃, and 58℃ respectively, then the set temperature for the time period of 02:00-03:00 is (60+55+58) / 3 = 57.6℃.
[0089] By using a moving average to smooth the forecast using the predicted temperature over the past three hours, drastic fluctuations in temperature forecasts can be reduced, resulting in a more stable forecast. Alternatively, averaging using data from the past four or more hours can achieve even better smoothing.
[0090] The embodiments of this application combine the prediction time to determine the set temperature of the wall-hung boiler, which reduces the drastic fluctuations in temperature prediction and makes the prediction results more stable.
[0091] refer to Figure 2 , Figure 2 This is the second schematic flowchart of the wall-hung boiler temperature control method provided in the embodiments of this application.
[0092] In this embodiment of the application, historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler are collected. Then, feature processing is performed on the collected data, and a dataset of the wall-hung boiler is constructed based on the feature-processed data.
[0093] The first predictive model is built based on the dataset. For example, to improve the accuracy of model training, data on boiler usage within the last 14 days (such as usage time periods, usage data, and weather data) is directly filtered out and not included in the model building. For users who have not used the boiler in the previous 48, 72, 96, 120, 144, and 168 hours, the predicted value is set to 0, meaning it is predicted that the user will not turn on the boiler during that hour. For users who have used the boiler in the previous 48, 72, 96, 120, 144, and 168 hours, the predictive model is built using the dataset.
[0094] The first prediction model predicts the probability of the wall-hung boiler being used each hour of the coming day. If the probability of use is 0, it means the boiler will not be used that hour, and the boiler's set temperature is directly set to the minimum temperature of 30℃. If the probability of use is 1, it means the boiler will be used that hour, and in this case, a second prediction model is needed to predict the heating temperature for that hour. Then, the predicted heating temperature is averaged based on the prediction duration. Finally, a recommended result table is determined based on the set temperature for each hour, so that the terminal can send control commands to the boiler based on this recommended result table, for example, sending control commands to the boiler according to the time points in the recommended result table.
[0095] In one specific embodiment, the steps of predicting the heating temperature of each wall-hung boiler for each hour on the next day, determining the set temperature based on the heating temperature, and then implementing temperature control of the wall-hung boiler based on the set temperature are as follows:
[0096] (1) Select the historical reported data of the wall-hung boiler over the past 14 days, combine it with weather data and data for each usage period, and generate corresponding data tables. Use the dataset composed of the data tables to train the prediction model.
[0097] (2) Calculate the number of days of use for each wall-hung boiler, and define a learning period flag. For boilers that have been used for 14 days or more, the learning period flag is set to 1; otherwise, it is set to 0. For boilers with a learning period flag of 1, the established model is used to predict the usage for each hour of the next day, generating the recommended data in the table below:
[0098] Device ID date Hour Set temperature Learning period markers
[0099] (3) Based on the recommended data, control commands are issued to each wall-hung boiler at specific time points to achieve temperature control of the wall-hung boiler.
[0100] This application's embodiments predict user behavior regarding the heating function of the wall-hung boiler in the coming day based on the boiler's usage behavior, weather data, and holiday data. Then, based on the prediction results and prediction duration, the boiler's set temperature is determined. This avoids manually setting the heating temperature, improves the efficiency of boiler temperature control, saves electricity, and avoids wasting electrical resources.
[0101] The following describes the wall-hung boiler temperature control device provided in the embodiments of this application. The wall-hung boiler temperature control device described below can be referred to in correspondence with the wall-hung boiler temperature control method described above.
[0102] refer to Figure 3 , Figure 3 This is a schematic diagram of the wall-hung boiler temperature control device provided in the embodiments of this application. The wall-hung boiler temperature control device of this application includes a construction module 301, a prediction module 302, and a control module 303.
[0103] The construction module 301 is used to construct the dataset of the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler.
[0104] Prediction module 302 is used to predict the temperature of the wall-hung boiler in future time periods based on the dataset;
[0105] The control module 303 is used to determine the set temperature of the wall-hung boiler in the future time period based on the temperature and predicted duration of each future time period, so as to perform temperature control on the wall-hung boiler based on the set temperature of each future time period.
[0106] The wall-hung boiler temperature control device provided in this application constructs a dataset of the wall-hung boiler, including historical usage data and historical weather data corresponding to various historical usage periods of the boiler. Based on the dataset, it predicts the boiler's temperature for future time periods. Based on the future temperatures and prediction durations, it determines the set temperatures for the boiler for each future time period, thereby controlling the boiler's temperature. This application predicts user behavior regarding the boiler's heating function in the coming day based on boiler usage behavior, weather data, and holiday data. Then, based on the prediction results and prediction durations, it determines the boiler's set temperature. This avoids manually setting the heating temperature, improves the efficiency of boiler temperature control, saves electricity, and avoids wasting electrical resources.
[0107] In one embodiment, the prediction module 302 is specifically used for:
[0108] The dataset is input into the first prediction model to obtain the probability of the wall-hung boiler being used in each future time period, as output by the first prediction model.
[0109] The usage probability is determined as a first probability value, and a subset of the dataset is input into a second prediction model to obtain the temperature of the wall-hung boiler in future time periods output by the second prediction module.
[0110] Wherein, the usage probability is a first probability value representing the use of the wall-hung boiler; the subset of the dataset includes historical usage data and historical weather data corresponding to each historical usage time period for which the usage probability is the first probability value; the first prediction model is obtained by training on a first sample set, which includes historical sample usage data and historical sample weather data corresponding to each historical sample usage time period for the wall-hung boiler; the second prediction model is obtained by training on a second sample set, which includes historical sample usage data and historical sample weather data corresponding to each historical sample usage time period for which the usage probability is the first probability value.
[0111] In one embodiment, the control module 303 is specifically used for:
[0112] If the predicted duration is determined to be less than the first set duration, the temperature output by the second prediction model shall be used as the set temperature of the wall-hung boiler for any future time period.
[0113] Alternatively, if the predicted duration is greater than or equal to the first set duration, the set temperature of the wall-hung boiler in any future time period is determined based on the temperatures of multiple consecutive time periods output by the second prediction model.
[0114] In one embodiment, the control module 303 is specifically used for:
[0115] Determine the average temperature corresponding to the temperature of multiple consecutive time periods output by the second prediction model;
[0116] The average temperature is used as the set temperature of the wall-hung boiler for any future time period.
[0117] In one embodiment, the control module 303 is further configured to:
[0118] The usage probability is determined as a second probability value, and the set temperature of the wall-hung boiler in future time periods is determined as the lowest temperature; the usage probability as a second probability value indicates that the wall-hung boiler is not used.
[0119] In one embodiment, the construction module 301 is specifically used for:
[0120] Obtain the usage time of the wall-hung boiler;
[0121] If the usage duration is determined to be greater than or equal to the second set duration, then historical usage data and historical weather data corresponding to each historical usage time period of the wall-hung boiler are collected to construct the dataset of the wall-hung boiler.
[0122] In one embodiment, the control module 303 is specifically used for:
[0123] Determine the time to send the temperature control command;
[0124] Based on the set temperatures for each future time period and the sending time, the temperature control command is sent to the wall-hung boiler; wherein, the wall-hung boiler adjusts the temperature based on the received temperature control command.
[0125] Figure 4 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 4 As shown, the electronic device may include a processor 410, a communications interface 420, a memory 430, and a communication bus 440, wherein the processor 410, the communications interface 420, and the memory 430 communicate with each other via the communication bus 440. The processor 410 can call logical instructions in the memory 430 to execute the following methods:
[0126] Construct a dataset for the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler;
[0127] Based on the dataset, predict the temperature of the wall-hung boiler in future time periods;
[0128] Based on the temperatures and predicted durations for each future time period, the set temperatures for the wall-hung boiler are determined for each future time period, so as to control the temperature of the wall-hung boiler based on the set temperatures for each future time period.
[0129] Furthermore, the logical instructions in the aforementioned memory 430 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0130] On the other hand, embodiments of this application also provide a non-transitory computer-readable storage medium storing a computer program thereon. When executed by a processor, the computer program implements the wall-hung boiler temperature control method provided in the above embodiments, including, for example:
[0131] Construct a dataset for the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler;
[0132] Based on the dataset, predict the temperature of the wall-hung boiler in future time periods;
[0133] Based on the temperatures and predicted durations for each future time period, the set temperatures for the wall-hung boiler are determined for each future time period, so as to control the temperature of the wall-hung boiler based on the set temperatures for each future time period.
[0134] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.
[0135] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.
[0136] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.
[0137] The above embodiments are for illustrative purposes only and are not intended to limit the scope of this application. Although this application has been described in detail with reference to the embodiments, those skilled in the art should understand that various combinations, modifications, or equivalent substitutions of the technical solutions of this application do not depart from the spirit and scope of the technical solutions of this application and should be covered within the scope of the claims of this application.
Claims
1. A method for temperature control of a wall-hung boiler, characterized in that, include: Construct a dataset for the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler; Based on the dataset, predict the temperature of the wall-hung boiler in future time periods; Based on the temperature and predicted duration of each future time period, the set temperature of the wall-hung boiler is determined for each future time period, so as to control the temperature of the wall-hung boiler based on the set temperature of each future time period. Determining the set temperature of the wall-hung boiler at any future time period includes: If the predicted duration is determined to be less than the first set duration, the temperature output by the second prediction model will be used as the set temperature of the wall-hung boiler for any future time period. The predicted duration refers to the time span considered when making temperature predictions, and different predicted durations correspond to different set temperatures. Alternatively, determine that the prediction duration is greater than or equal to the first set duration, determine the average temperature corresponding to the temperatures of multiple consecutive time periods output by the second prediction model, and use the average temperature as the set temperature of the wall-hung boiler for any future time period.
2. The wall-hung boiler temperature control method according to claim 1, characterized in that, The prediction of the temperature of the wall-hung boiler in future time periods based on the dataset includes: The dataset is input into the first prediction model to obtain the probability of the wall-hung boiler being used in each future time period, as output by the first prediction model. The usage probability is determined as a first probability value, and a subset of the dataset is input into a second prediction model to obtain the temperature of the wall-hung boiler in future time periods as output by the second prediction model. Wherein, the usage probability is a first probability value representing the use of the wall-hung boiler; the subset of the dataset includes historical usage data and historical weather data corresponding to each historical usage time period for which the usage probability is the first probability value; the first prediction model is obtained by training on a first sample set, which includes historical sample usage data and historical sample weather data corresponding to each historical sample usage time period for the wall-hung boiler; the second prediction model is obtained by training on a second sample set, which includes historical sample usage data and historical sample weather data corresponding to each historical sample usage time period for which the usage probability is the first probability value.
3. The wall-hung boiler temperature control method according to claim 2, characterized in that, After inputting the dataset into the first prediction model and obtaining the usage probability of the wall-hung boiler in future time periods output by the first prediction model, the method further includes: The usage probability is determined as a second probability value, and the set temperature of the wall-hung boiler in future time periods is determined as the lowest temperature; the usage probability as a second probability value indicates that the wall-hung boiler is not used.
4. The wall-hung boiler temperature control method according to claim 1, characterized in that, The dataset used to construct the wall-hung boiler includes: Obtain the usage time of the wall-hung boiler; If the usage duration is determined to be greater than or equal to the second set duration, then historical usage data and historical weather data corresponding to each historical usage time period of the wall-hung boiler are collected to construct the dataset of the wall-hung boiler.
5. The wall-hung boiler temperature control method according to claim 1, characterized in that, The temperature control of the wall-hung boiler based on the set temperatures for each future time period includes: Determine the time to send the temperature control command; Based on the set temperatures for each future time period and the sending time, the temperature control command is sent to the wall-hung boiler; wherein, the wall-hung boiler adjusts the temperature based on the received temperature control command.
6. A temperature control device for a wall-hung boiler, characterized in that, include: The construction module is used to build the dataset of the wall-hung boiler, which includes historical usage data and historical weather data corresponding to each historical usage period of the wall-hung boiler; The prediction module is used to predict the temperature of the wall-hung boiler in future time periods based on the dataset. The control module is used to determine the set temperature of the wall-hung boiler in the future time period based on the temperature and predicted duration of each future time period, so as to control the temperature of the wall-hung boiler based on the set temperature of each future time period. The control module is further configured to determine that the prediction duration is less than a first set duration, and use the temperature output by the second prediction model as the set temperature of the wall-hung boiler for any future time period; the prediction duration refers to the time span considered when making temperature predictions, and different prediction durations correspond to different set temperatures; or, determine that the prediction duration is greater than or equal to the first set duration, determine the average temperature corresponding to the temperatures of multiple consecutive time periods output by the second prediction model, and use the average temperature as the set temperature of the wall-hung boiler for any future time period.
7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the wall-hung boiler temperature control method as described in any one of claims 1 to 5.
8. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the wall-hung boiler temperature control method as described in any one of claims 1 to 5.